EEGChaT: A Transformer-Based Modular Channel Selector for SEEG Analysis

• URL: http://arxiv.org/abs/2510.13592v1
• Date: Wed, 15 Oct 2025 14:22:07 GMT
• Title: EEGChaT: A Transformer-Based Modular Channel Selector for SEEG Analysis
• Authors: Chen Wang, Yansen Wang, Dongqi Han, Zilong Wang, Dongsheng Li,
• Abstract summary: We propose EEGChaT, a novel Transformer-based channel selection module for SEEG data analysis.<n>We show that EEGChaT consistently improves decoding accuracy, achieving up to 17% absolute gains.<n>Our results suggest that EEGChaT is an effective and generalizable solution for channel selection in high-dimensional SEEG analysis.
• Score: 33.75063804360241
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Analyzing stereoelectroencephalography (SEEG) signals is critical for brain-computer interface (BCI) applications and neuroscience research, yet poses significant challenges due to the large number of input channels and their heterogeneous relevance. Traditional channel selection methods struggle to scale or provide meaningful interpretability for SEEG data. In this work, we propose EEGChaT, a novel Transformer-based channel selection module designed to automatically identify the most task-relevant channels in SEEG recordings. EEGChaT introduces Channel Aggregation Tokens (CATs) to aggregate information across channels, and leverages an improved Attention Rollout technique to compute interpretable, quantitative channel importance scores. We evaluate EEGChaT on the DuIN dataset, demonstrating that integrating EEGChaT with existing classification models consistently improves decoding accuracy, achieving up to 17\% absolute gains. Furthermore, the channel weights produced by EEGChaT show substantial overlap with manually selected channels, supporting the interpretability of the approach. Our results suggest that EEGChaT is an effective and generalizable solution for channel selection in high-dimensional SEEG analysis, offering both enhanced performance and insights into neural signal relevance.

Related papers

• Optimizing Brain-Computer Interface Performance: Advancing EEG Signals Channel Selection through Regularized CSP and SPEA II Multi-Objective Optimization [13.981941979747305]
  RCSP exhibits efficacy in the discrimination and classification of EEG signals. We employ a state-of-the-art approach in the selection of a subset of channels from a multichannel EEG signal with MI tasks.
  arXiv  Detail & Related papers  (2024-04-26T00:04:41Z)
• Physics-informed and Unsupervised Riemannian Domain Adaptation for Machine Learning on Heterogeneous EEG Datasets [53.367212596352324]
  We propose an unsupervised approach leveraging EEG signal physics. We map EEG channels to fixed positions using field, source-free domain adaptation. Our method demonstrates robust performance in brain-computer interface (BCI) tasks and potential biomarker applications.
  arXiv  Detail & Related papers  (2024-03-07T16:17:33Z)
• An EEG Channel Selection Framework for Driver Drowsiness Detection via Interpretability Guidance [7.657035689406044]
  Drowsy driving has a crucial influence on driving safety, creating an urgent demand for driver drowsiness detection. EEG signal can accurately reflect the mental fatigue state and thus has been widely studied in drowsiness monitoring. We propose an Interpretability-guided Channel Selection (ICS) framework for the driver drowsiness detection task.
  arXiv  Detail & Related papers  (2023-04-26T13:24:37Z)
• Learning Signal Representations for EEG Cross-Subject Channel Selection and Trial Classification [0.3553493344868413]
  We introduce an algorithm for subject-independent channel selection of EEG recordings. It exploits channel-specific 1D-Convolutional Neural Networks (1D-CNNs) as feature extractors in a supervised fashion to maximize class separability. After training, the algorithm can be exploited by transferring only the parametrized subgroup of selected channel-specific 1D-CNNs to new signals from new subjects.
  arXiv  Detail & Related papers  (2021-06-20T06:22:16Z)
• Robust learning from corrupted EEG with dynamic spatial filtering [68.82260713085522]
  Building machine learning models using EEG recorded outside of the laboratory requires robust methods to noisy data and randomly missing channels. We propose dynamic spatial filtering (DSF), a multi-head attention module that can be plugged in before the first layer of a neural network. We tested DSF on public EEG data encompassing 4,000 recordings with simulated channel corruption and on a private dataset of 100 at-home recordings of mobile EEG with natural corruption.
  arXiv  Detail & Related papers  (2021-05-27T02:33:16Z)
• End-to-end learnable EEG channel selection with deep neural networks [72.21556656008156]
  We propose a framework to embed the EEG channel selection in the neural network itself. We deal with the discrete nature of this new optimization problem by employing continuous relaxations of the discrete channel selection parameters. This generic approach is evaluated on two different EEG tasks.
  arXiv  Detail & Related papers  (2021-02-11T13:44:07Z)
• Cross-Correlation Based Discriminant Criterion for Channel Selection in Motor Imagery BCI Systems [1.240096657086732]
  We propose a cross-correlation based discriminant criterion (XCDC) which assesses the importance of a channel for discriminating the mental states of different motor imagery (MI) tasks. XCDC significantly reduces the amount of channels without compromising classification accuracy compared to the all-channel setups.
  arXiv  Detail & Related papers  (2020-12-03T08:32:47Z)
• Learning from Heterogeneous EEG Signals with Differentiable Channel Reordering [51.633889765162685]
  CHARM is a method for training a single neural network across inconsistent input channels. We perform experiments on four EEG classification datasets and demonstrate the efficacy of CHARM.
  arXiv  Detail & Related papers  (2020-10-21T12:32:34Z)
• Data-Driven Symbol Detection via Model-Based Machine Learning [117.58188185409904]
  We review a data-driven framework to symbol detection design which combines machine learning (ML) and model-based algorithms. In this hybrid approach, well-known channel-model-based algorithms are augmented with ML-based algorithms to remove their channel-model-dependence. Our results demonstrate that these techniques can yield near-optimal performance of model-based algorithms without knowing the exact channel input-output statistical relationship.
  arXiv  Detail & Related papers  (2020-02-14T06:58:27Z)
• DeepSIC: Deep Soft Interference Cancellation for Multiuser MIMO Detection [98.43451011898212]
  In multiuser multiple-input multiple-output (MIMO) setups, where multiple symbols are simultaneously transmitted, accurate symbol detection is challenging. We propose a data-driven implementation of the iterative soft interference cancellation (SIC) algorithm which we refer to as DeepSIC. DeepSIC learns to carry out joint detection from a limited set of training samples without requiring the channel to be linear.
  arXiv  Detail & Related papers  (2020-02-08T18:31:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.